agentleFS
Sign inStart free
AgentWrapperAgentWrapper/agent-orchestrator/.agents/skills/pr-description/SKILL.md

pr-description

Skill14k starsChanged 5 days agoApache-2.0View on GitHub

Write and maintain pull request descriptions in this repository, including the required change-count header, the before-and-after section, and screenshots or recordings for visible changes.

We split this skill into the rules it gives an agent

7 rules. 0 are common, 4 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 82 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use the section order in .github/pull_request_template.md: change-count header, What, Why, Before / After, How, Testing, Checklist.

    line 8
  2. Distinctive:

    Tests: test code, fixtures, snapshots, and test-only helpers.

    line 32
  3. Very specific:

    Every PR has a ## Before / After section with a two-column table, one row per behavior that changed:

    line 42
  4. Very specific:

    No user-visible change: write No user-visible change and one line saying why, such as an internal refactor or a test-only change.

    line 56
  5. Distinctive:

    Never commit screenshots or recordings to the repository.

    line 67
  6. Distinctive:

    After creating or updating the PR, read the published description and verify that:

    line 74
  7. Distinctive:

    every image and recording in Before / After, or in a PR comment, loads.

    line 77

“Common” is measured: kept by at least 6 in 10 of the 82 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

PR description

Use the section order in .github/pull_request_template.md: change-count header, What, Why, Before / After, How, Testing, Checklist. Preserve the rest of an existing PR description when updating it.

Change-count header

Begin every PR description with these three lines, using Markdown hard line breaks so each renders separately:

Code changes: +<added> -<deleted>
Tests: +<added> -<deleted>
Others: +<added> -<deleted>

Calculate the numbers from the net diff against the PR's actual base. For a local branch, use git diff --numstat <base>...<head>. After pushing, prefer GitHub's per-file additions and deletions. Recalculate after the final push rather than summing commit churn or estimating counts.

Count every changed file exactly once:

  • Code changes: handwritten implementation, including SQL, migrations, styles, and executable scripts.
  • Tests: test code, fixtures, snapshots, and test-only helpers.
  • Others: generated or vendored files, lockfiles, documentation, configuration, and assets. Generated output belongs here even when it contains source code.

Show +0 -0 for empty categories. Binary files have no line count; mention their count separately when present. Add a brief qualifier when useful, such as Others: +11 -0 (generated sqlc).

Before / After

Every PR has a ## Before / After section with a two-column table, one row per behavior that changed:

| Before | After |
| --- | --- |
| ![Before: empty model list](before.png) | ![After: list filtered to six models](after.png) |
| `ao session ls` exits 1 when a project has no sessions | Prints `No sessions` and exits 0 |
  • UI changes need a screenshot of each changed state, before and after. Use a short recording for flows, animations, focus or keyboard behavior, and timing.
  • Non-visual changes compare observable behavior: command output, API responses, errors, logs, or measured numbers with their units.
  • No user-visible change: write No user-visible change and one line saying why, such as an internal refactor or a test-only change.

Capture both sides from the real app with the same screen, window size, and data, so they compare directly. Take the before capture from the PR's base branch. The ao-desktop-dev skill launches the desktop app from a checkout.

Screenshots and GIFs go in the table. GitHub renders a video player only for a bare attachment URL on its own line, so put MP4 or MOV recordings on their own line below the table, with one line saying what they show.

Never commit screenshots or recordings to the repository. Attach them in the PR description, or in a PR comment when the description gets long. If you cannot upload, give the capture file paths to the person who will attach them. Remove secrets, tokens, and personal data from every capture.

Verify

After creating or updating the PR, read the published description and verify that:

  • its opening lines match the current GitHub diff counts and required order;
  • every image and recording in Before / After, or in a PR comment, loads.

Download now (ZIP)

Trending

Less talk lately.about the whole repository

Dec 2025: 0 mentionsJan 2026: 0 mentionsFeb 2026: 0 mentionsMar 2026: 0 mentionsApr 2026: 0 mentionsMay 2026: 0 mentionsJun 2026: 7 mentionsJul 2026: 40 mentionsAug 2026: 4 mentionsSep 2026: 5 mentionsOct 2026: 3 mentionsNov 2026: 0 mentions
Dec 2025Jun 2026Nov 2026
Mentions a month of the AgentWrapper/agent-orchestrator repository that our weekly crawl found. There is no adoption data for this file yet.

Who's talking about AgentWrapper/agent-orchestrator

The biggest 5 of 59 mentions linking to the repository that our crawl found. Each line is their own headline.

See all 59

Talked about on GitHub, the web, Bluesky and YouTube (59 times).

On GitHub · 50

45 more on GitHub

On YouTube · 1

  • Other versions90 projects use a version of this.

    Word for word · 3

    1. ComposioHQ/agent-orchestrator★ 14k100% same
    2. OrchestratorInc/agent-orchestrator★ 14k100% same
    3. Untrivial-ai/agent-orchestrator★ 14k100% same

    Edited · 0

    None found.

    Wrote their own version · 87

    1. jdx/mise★ 36ksame name
    2. zulip/zulip★ 26ksame name
    3. Nagi-ovo/gemini-voyager★ 21ksame name
    4. pipecat-ai/pipecat★ 17ksame name
    5. sanity-io/sanity★ 6.4ksame name
    6. vimeo/psalm★ 5.9ksame name
    7. pytorch/torchtitan★ 5.9ksame name
    8. basicmachines-co/basic-memory★ 4.4ksame name
    9. dotnet/fsharp★ 4.3ksame name
    10. TanStack/ai★ 3.3ksame name

    77 more not listed

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • Used alongsideProjects with it also use commit-message, dependency-audit and 8 more.

    Other files people use alongside this one.

    Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
    • GitHubSkill

      commit-message

      Generate conventional commit messages - use when creating commits, writing commit messages, or asking for git commit help

      Also in 8 projects that use this

    • francogalfreSkill

      dependency-audit

      Audits package.json dependencies for outdated packages, security vulnerabilities, unnecessary deps, and version issues. Use when the user says "audit my dependencies", "check my packages", "what deps should I update", "clean up package.json", "are there security issues in my deps", or pastes a package.json.

      Also in 3 projects that use this

    • PydanticSkill

      i-have-adhd

      Shape every response for an ADHD reader who reviews the work but does not do the coding — the agent does. Use whenever responding to ANY message — coding, debugging, planning, casual. Lead with the result or the decision. Surface anything needing the user's input as a structured question, never buried in prose they'll skim past. No preamble, no recap, no closers. State errors matter-of-factly. Make finished work visible. Trigger even on casual messages and even when brevity wasn't requested.

      Also in 3 projects that use this

    • HashiCorpSkill

      changelog

      Add a `.changelog/<PR_NUMBER>.txt` entry for a GitHub Pull Request, commit, and push.

      Also in 5 projects that use this

    • LLl0k0laDSkill

      code-review-and-quality

      Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.

      Also in 3 projects that use this

    • simo97Skill

      obsidian-vault

      Also in 3 projects that use this

  • In this repository6 other files it gives its agents.

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free